Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3538 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3347. Min Range: -6.3347
Max Act: 6.3347. Min Act: -0.1700
Data Index: 294861 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3347. Min Range: -6.3347
Max Act: 6.0847. Min Act: -0.1700
Data Index: 5441758 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3347. Min Range: -6.3347
Max Act: 6.0222. Min Act: -0.1700
Data Index: 1243865 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3347. Min Range: -6.3347
Max Act: 5.9909. Min Act: -0.1700
Data Index: 3743328 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3347. Min Range: -6.3347
Max Act: 5.9597. Min Act: -0.1700
Data Index: 5104464 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3347. Min Range: -6.3347
Max Act: 5.9284. Min Act: -0.1700
Data Index: 4328745 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3347. Min Range: -6.3347
Max Act: 5.9284. Min Act: -0.1700
Data Index: 1747945 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3347. Min Range: -6.3347
Max Act: 5.8972. Min Act: -0.1700
Data Index: 4199922 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3347. Min Range: -6.3347
Max Act: 5.8972. Min Act: -0.1700
Data Index: 6853400 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3347. Min Range: -6.3347
Max Act: 5.8659. Min Act: -0.1700
Data Index: 4766284 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3347. Min Range: -6.3347
Max Act: 5.8659. Min Act: -0.1700
Data Index: 1672845 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3347. Min Range: -6.3347
Max Act: 5.8659. Min Act: -0.1700
Data Index: 1669437 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3347. Min Range: -6.3347
Max Act: 5.8347. Min Act: -0.1700
Data Index: 8818975 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3347. Min Range: -6.3347
Max Act: 5.8034. Min Act: -0.1700
Data Index: 7585843 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3347. Min Range: -6.3347
Max Act: 5.7722. Min Act: -0.1700
Data Index: 763512 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3347. Min Range: -6.3347
Max Act: 5.7409. Min Act: -0.1700
Data Index: 2460211 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3347. Min Range: -6.3347
Max Act: 5.7409. Min Act: -0.1700
Data Index: 8656158 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3347. Min Range: -6.3347
Max Act: 5.7097. Min Act: -0.1700
Data Index: 7191941 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3347. Min Range: -6.3347
Max Act: 5.7097. Min Act: -0.1700
Data Index: 7226830 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3347. Min Range: -6.3347
Max Act: 5.7097. Min Act: -0.1700
Data Index: 5372344 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #19